XZXu Zhang

Xu Zhang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Xu Zhang has a total of 30 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Facial Expression and Behavior Modeling from Digital Avatars to Expressive Humanoid Robots: A Review

    by Xu Zhang, Longbing Cao

    Endowing humanoid robots with expressive, controllable, and robust facial expressions and behaviors is essential for advancing human-like humanoid-human interaction across social, healthcare, and service domains. However, transforming the semantic richness and flexibility of virtual avatars into the mechanical, real-time, and calibration constraints of physical humanoids remains a fundamental challenge. This survey reviews facial expression and behavior modeling for both and analyzes their virtual-to-physical gaps from a deployment-oriented perspective. Our review is organized along three axes: (i) modeling paradigms , with emphasis on actuator compatibility and transferability; (ii) expression control strategies , assessed for their potential to enable robust robotic deployment; and (iii) deployment dimensions , which examine the challenges of parameter-to-actuator mapping, calibration, and real-time operation. This survey provides a critical synthesis of the tradeoffs between expressive fidelity and hardware feasibility. We analyze persistent gaps between algorithmic advances and embodied realization, and review the datasets, metrics, and evaluation frameworks necessary for advancing expressive humanoids and their facial expression and behavior modeling. Finally, we identify open challenges and future research directions, including multimodal coordination, adaptive personalization, and standardized evaluation, providing guidance for next-generation expressive human-like humanoids, and systematically integrating advances in humanoid modeling with actionable deployment of humanoid facial expressions and behaviors.

  • Open Access

    Exploiting dynamic spatio-temporal correlations for origin-destination demand prediction

    by Yongshun Gong, Piao Yu, Xu Zhang, Xinxin Zhang, Xiushan Nie, Haoliang Sun


  • A Mutually Enhancement Network for Superpixel Segmentation and Classification of Hyperspectral Image

    by Mengxin Cao, Yongmin Li, Xu Zhang, Guixin Zhao, Guohua Lv, Aimei Dong, Jinyong Cheng, Wei Li, Xiangjun Dong

    Most existing hyperspectral image (HSI) classification methods primarily focus on capturing subtle spectral variations by leveraging local spectral–spatial cues derived from patch-level representations. However, limited attention has been given to exploring the global spatial contextual correlations among pixels of HSI. In this study, we propose the superpixel segmentation and classification mutual enhancement network ( $\mathbf {S}^{2}$ CMEN), a novel framework that integrates global spatial correlations with spectral information through the mutual enhancement of superpixel segmentation and classification. Specifically, a global spatial adaptive module (GSAM) is designed to obtain the direct correlation of the global classes in HSI. It consists of an adaptive spectral-superpixel network (ASSN) and a graph convolutional network (GCN), forming a synergistic architecture that effectively captures global spatial relationships by adaptively deriving superpixel results from HSIs. Notably, GSAM offers a transferable global spatial representation for HSI tasks, enabling integration with other spectral feature extraction models. Furthermore, we develop a spatial–spectral fusion module (SSFM) to obtain comprehensive spectral features and fuse them with the extracted global spatial features. Finally, under the constraint of a unit loss, the mutual enhancement strategy (MES) can make the superpixel segmentation loss and the classification loss mutually enhance each other for better performance. We conducted extensive experiments on three public datasets. The proposed $\mathbf {S}^{2}$ CMEN achieves overall classification accuracies of 97.38%, 92.33%, and 91.38% on Indian Pines (IPs), Pavia University (PU), and Houston, respectively, consistently surpassing existing state-of-the-art methods.


  • Enhancing urban flow prediction via mutual reinforcement with multi-scale regional information

    by Xu Zhang, Mengxin Cao, Yongshun Gong, Xiaoming Wu, Xiangjun Dong, Ying Guo, Long Zhao, Chengqi Zhang


  • Spatial-Spectral–Semantic Cross-Domain Few-Shot Learning for Hyperspectral Image Classification

    by Mengxin Cao, Xu Zhang, Jinyong Cheng, Guixin Zhao, Wei Li, Xiangjun Dong

    Preprocessing procedures are commonly employed to reduce water-absorption bands and noise in hyperspectral images (HSI). Nevertheless, they typically do not entirely eradicate noise. This is especially evident in scenarios that necessitate data of exceptional quality, such as cross-domain few-shot classification tasks. Within these specific conditions, the influence of remaining background noise on the ultimate results of classification is substantial. Furthermore, the presence of sample selection biases in the few-shot task might lead to the emergence of false statistical correlations between data from distinct domains, resulting in a decrease in the model’s ability to generalize. We propose a new method called spatial-spectral-semantic cross-domain few-shot learning ( S 3 CFSL ) to address the challenge. This method promotes the learning of transferable information by incorporating feature denoising operations in the feature extraction process to restore essential information. Concurrently, it enhances cross-domain distributional consistency by introducing a semantic-aware strategy to strengthen the association between cross-domain data and semantic information. Specifically, the spatial and spectral dual channels (SSDC), in conjunction with the cross spatial spectral Transformer (CSST), are designed as a feature extractor to acquire interactive spatial-spectral features. The feature-denoising operations can further acquiring transferable information from cross-domain features, thus facilitating meta-learning in both the source domain (SD) and the target domain (TD). Meanwhile, a semantic enhanced domain alignment (SEDA) is designed to promote domain adaptation by using a semantic-aware strategy, which significantly enhances distributional consistency for cross-domain tasks. Our results exhibit exceptional classification efficacy in comparison to other state-of-the-art approaches on three public HSI datasets.


  • Spatio-temporal fusion and contrastive learning for urban flow prediction

    by Xu Zhang, Yongshun Gong, Chengqi Zhang, Xiaoming Wu, Ying Guo, Wenpeng Lu, Long Zhao, Xiangjun Dong


  • Open Access

    Mask- and Contrast-Enhanced Spatio-Temporal Learning for Urban Flow Prediction

    by Xu Zhang, Yongshun Gong, Xinxin Zhang, Xiaoming Wu, Chengqi Zhang, Xiangjun Dong

    As a critical mission of intelligent transportation systems, urban flow prediction (UFP) benefits in many city services including trip planning, congestion control, and public safety. Despite the achievements of previous studies, limited efforts have been observed on simultaneous investigation of the heterogeneity in both space and time aspects. That is, regional correlations would be variable at different timestamps. In this paper, we propose a spatio-temporal learning framework with mask and contrast enhancements to capture spatio-temporal variabilities among city regions. We devise a mask-enhanced pre-training task to learn latent correlations across the spatial and temporal dimensions, and then a graph-based method is developed to extract the significance of regions by using the inter-regional attention weights. To further acquire contrastive correlations of regions, we elaborate a pre-trained contrastive learning task with the global-local cross-attention mechanism. Thereafter, two well-trained encoders have strong capability to capture latent spatio-temporal representations for the flow forecasting with time-varying. Extensive experiments conducted on real-world urban flow datasets demonstrate that our method compares favorably with other state-of-the-art models.